Rule Discovery

Shafic, S., K. Shaalan, and A. Rafea, "Macro Association Rule Discovery: Impact of Environmental indicators Changes on Life Assurance Business", Egyptian Informatics Journal, vol. 3, no. 2: Faculty of Comptuers and Information, pp. 96–114, dec, 2002. Abstractmacro_assoc_rule_disc_fci_journal.pdf

Knowledge discovery in financial organization have been built and operated mainly to support decision making using knowledge as strategic factor.In this paper, we investigate the use of association rule mining as an underlying technology for knowledge discovery in insurance business. Existing association rule algorithms and its extensions are inefficient in mining association rules in such data characteristics. We introduce algorithms for discovering knowledge in the form of association rules, suitable for data characteristics. Proposed data mining techniques is a hybrid of clustering partitioning and multi level rule induction. The proposed tool is managed by a repository meta model instantiated by meta-data libraries specific to insurance domain. It is implemented on a PC running on Ms Windows 2000. Samples of life data are extracted from different geographical locations of an Egyptian insurance company covering ten years. By using the induced rules, the decision- maker can define the horizontal expansion of marketing activities on new geographical area, or vertically empower the marketing forces in existing geographical area. Keywords: insurance data characteristics, macro association rules, clustering partitioning, preprocessing &transformation, OLAP aggregation, ontology, data warehouse

Rafea, A., S. Shafik, and K. Shaalan, "An Interactive System for Association Rule Discovery for Life Assurance", International Conference on Computer, Communication and Control Technologies (CCCT '04), Texas, USA, pp. 32–37, aug, 2004. Abstractrule_disc_ccct_2004.pdf

Knowledge discovery in financial organization have been built and operated mainly to support decision making using knowledge as strategic factor.In this paper, we investigate the use of association rule mining as an underlying technology for knowledge discovery in insurance business. Existing association rule algorithms and its extensions are inefficient in mining association rules in such data characteristics. We introduce algorithms for discovering knowledge in the form of association rules, suitable for data characteristics. Proposed data mining techniques is a hybrid of clustering partitioning and multi level rule induction. The proposed tool is managed by a repository meta model instantiated by meta-data libraries specific to insurance domain. It is implemented on a PC running on Ms Windows 2000. Samples of life data are extracted from different geographical locations of an Egyptian insurance company covering ten years. By using the induced rules, the decision- maker can define the horizontal expansion of marketing activities on new geographical area, or vertically empower the marketing forces in existing geographical area. Keywords: insurance data characteristics, macro association rules, clustering partitioning, preprocessing &transformation, OLAP aggregation, ontology, data warehouse

Tourism